The proceedings contain 80 papers. The topics discussed include: randomized protocols for resilient peer-to-peer networks;evaluating the performance of 5G NR in indoor environments: an experimental study;an approach t...
The proceedings contain 80 papers. The topics discussed include: randomized protocols for resilient peer-to-peer networks;evaluating the performance of 5G NR in indoor environments: an experimental study;an approach towards reducing training time of the input doubling method via clustering for middle-sized data analysis;analysis of legislative framework governing biometric data;designing a testbed for privacy-preserving voice-based social networks;classical machine learning and large models for text-based emotion recognition;one hop routing optimization approach using machine learning;toward an enhanced stock market forecasting with machine learning and deep learning models;smart agriculture system based on IoT reference architecture and service choreography;and privacy-preserving crime reporting and rewarding in the presence of active insider and outsider adversaries.
Simulation optimization has been the focus of numerous studies in the area of operations research, with many studies integrating optimization algorithms with simulation models to improve decision-making. Although usef...
详细信息
This paper presents the genetic algorithm-based optimal design method of the resonant converters. The developed software finds an optimal parameter set of the resonant converter for achieving the rated output power wi...
详细信息
To create a future society based on cyber-physical systems, we need real-time digital twins made with cameras and sensors. The challenge is making this energy-efficient. A model in [1] suggests dividing video analysis...
详细信息
In this paper, we present a novel transport-lot optimization problem at the boundary between the continuous casters and the hot-rolling in steel production. The problem and the corresponding solver are part of a syste...
详细信息
Deep Neural Networks (DNNs) have been widely applied in many fields for decades, and a standard method for deploying them on embedded systems involves using accelerators. However, due to the resource constraints of em...
详细信息
ISBN:
(纸本)9798350300246
Deep Neural Networks (DNNs) have been widely applied in many fields for decades, and a standard method for deploying them on embedded systems involves using accelerators. However, due to the resource constraints of embedded systems, improving energy and computing efficiency becomes one of the research challenges in this domain. DNN model optimization and NAS (Neural Architecture Searching) are commonly used to strengthen the DNN model running efficiency on an embedded system. However, because the system's runtime workloads are varied in practical situations, to further improve the computing efficiency of the system at runtime, real-time hardware and software design space exploration is required to ensure the system is running at the optimal time state at runtime. This paper presents a comprehensive modelling and analysis approach for the performance data (e.g., latency, energy consumption, accuracy, etc.) collected from an AMD-Xilinx heterogeneous MPSoC platform equipped with multiple DNN accelerators. The results demonstrate that the relationships between accuracy loss, hardware performance, and model size are significantly correlated. Furthermore, an appropriate hardware and software configuration could be obtained by giving constraints at runtime.
The optimization of complex industrial systems represents a class of difficult problems, due to their embodiment in the physical world, and whose search spaces are disrupted, non-linear and potentially vast. Their par...
详细信息
Parallel elastic actuators (PEA) are widely applied for robotic applications with asymmetric load requirement. The elastic components are included in the systems aiming to reduce the actuation peak torque required fro...
详细信息
ISBN:
(纸本)9798350381566;9798350381559
Parallel elastic actuators (PEA) are widely applied for robotic applications with asymmetric load requirement. The elastic components are included in the systems aiming to reduce the actuation peak torque required from the electric motors. However, higher torque may be required during the opposite motion. The fused deposition modeling technique allows fabrication of 3D printed composite spiral torsion springs for compact modular PEAs. The antagonistic design enables using the springs to support moment in bidirectional. Preloading is substantially required to ensure the winding deformation of both springs. The design of spring stiffness and equilibrium is the major challenge to minimize the actuation peak torque and power consumption. In this paper, the behavior of the parallel elastic actuator with preloaded springs while subjected to the pure stiffness load is observed in three cases: the PEA's spring has lower, higher, and the same stiffness as the load. The position and current of the brushless DC motor driven by the ODrive Pro motor controller are recorded. The experimental setup allows characterization of the spring component and the PEA using different number of spring stacks. The results of this study can be used as a reference for further designing of antagonistic PEAs with preload for asymmetric load support.
The proceedings contain 27 papers. The topics discussed include: applying conformance checking on virtual laboratory experiments;assortment optimization in sheet metal procurement with k-means;timing analysis of the s...
ISBN:
(纸本)9788885741775
The proceedings contain 27 papers. The topics discussed include: applying conformance checking on virtual laboratory experiments;assortment optimization in sheet metal procurement with k-means;timing analysis of the sanitization process due to the COVID-19 pandemic in an elementary school using simulation;a generic framework for simulation-based optimization using high-level architecture;a conceptual training simulator for the assembly of electric vehicle batteries in virtual reality;modelling supply chain coordination using multidimensional auctions;modelling shifting trends over time via topic analysis of text documents;discrete-event simulation of construction safety inspections;simulation study on the influence of design on the performance of dynamic hybrid pallet warehouses;and design and analysis of alternatives for the supply of components within the production facilities of new customers of a company with a full-service provider model.
Recent computerized and control technology makes it less difficult to design a controller for an electrohydraulic actuator (EHA). This paper aims to improve the controllers using an optimization algorithm. A pump, con...
详细信息
暂无评论